Instructions to use kabelomalapane/Af-En with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use kabelomalapane/Af-En with Transformers:
# Use a pipeline as a high-level helper # Warning: Pipeline type "translation" is no longer supported in transformers v5. # You must load the model directly (see below) or downgrade to v4.x with: # 'pip install "transformers<5.0.0' from transformers import pipeline pipe = pipeline("translation", model="kabelomalapane/Af-En")# Load model directly from transformers import AutoTokenizer, AutoModelForMultimodalLM tokenizer = AutoTokenizer.from_pretrained("kabelomalapane/Af-En") model = AutoModelForMultimodalLM.from_pretrained("kabelomalapane/Af-En") - Notebooks
- Google Colab
- Kaggle
Kabelo Malapane commited on
Commit ·
667202b
1
Parent(s): fb57318
Update README.md
Browse files
README.md
CHANGED
|
@@ -15,10 +15,18 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 15 |
|
| 16 |
# En-Af
|
| 17 |
|
| 18 |
-
This model is a fine-tuned version of [Helsinki-NLP/opus-mt-
|
| 19 |
It achieves the following results on the evaluation set:
|
| 20 |
-
|
| 21 |
-
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 22 |
|
| 23 |
## Model description
|
| 24 |
|
|
|
|
| 15 |
|
| 16 |
# En-Af
|
| 17 |
|
| 18 |
+
This model is a fine-tuned version of [Helsinki-NLP/opus-mt-af-en](https://huggingface.co/Helsinki-NLP/opus-mt-en-af) on the None dataset.
|
| 19 |
It achieves the following results on the evaluation set:
|
| 20 |
+
Before training:
|
| 21 |
+
- 'eval_bleu': 46.1522519
|
| 22 |
+
- 'eval_loss': 2.5693612
|
| 23 |
+
|
| 24 |
+
After training:
|
| 25 |
+
- Loss: 1.7516168
|
| 26 |
+
- Bleu: 55.3924697
|
| 27 |
+
|
| 28 |
+
|
| 29 |
+
|
| 30 |
|
| 31 |
## Model description
|
| 32 |
|